Finger-Vein Based Biometric Security System

Published on November 2016 | Categories: Documents | Downloads: 39 | Comments: 0 | Views: 352
of 4
Download PDF   Embed   Report

IJRET : International Journal of Research in Engineering and Technology



IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308

Volume: 02 Issue: 12 | Dec-2013, Available @ 197

Jose Anand
, T. G. Arul Flora
, Anu Susan Philip

Associate Professor,
2, 3
Assistant Professor, Department of Electronics and Communication Engineering,
KCG College of Technology, Chennai, India

Finger vein recognition is a kind of biometric authentication system. This is one among many forms of biometrics used to recognize
the individuals and to verify their identity. This paper presents a finger vein authentication system using template matching.
Implementation using Matlab shows that the finger vein authentication system performs well for user identification.

Keywords – biometric, feature extraction, figure vein, security system.
Finger vein [13] biometric authentication is a recent
identification system in this modern era. This technology is
used for wide variety of applications including credit card
authentication, automobile security, employee time and
attendance tracking, computer and network authentication, and
so on.

Like fingerprints [12] or iris patterns, finger vein based blood
vessel patterns are unique for each individual. Finger vein
based blood vessel pattern have high security because the
veins are located under the surface of the skin. The
fingerprints can be cheated by dummy finger fitted with a
copied fingerprint, but the finger vein based identification
system is highly secure for authentication.

The iris pattern recognition [5] is known for low error rates of
authentication, but some users feel psychological resistance to
the direct application of light rays into their eyes. In addition
to this, precise positioning of the eyes is required for accurate
iris authentication. So the iris authentication system is
provided with high-cost position adjustment mechanisms for
the accurate recognition.

For authentication application the pattern of the finger vein
[14] is stored in a database. The finger is placed on an attester
terminal which contains a near-infrared, light emitting diode
light source and a monochrome charge coupled device camera.
The hemoglobin present in the blood absorbs the near infrared
light emitting diode light and makes the vein to appear as dark
pattern. The recorded image is digitized and stored in the
database. During authentication, the finger vein is scanned and
is compared with the image in the database.

The rest of the paper is organized as follows. Section 2
reviews about the related literature and section 3 describe the
finger-vein based security system for authentication needed
real-time applications. Section 4 details the performance
evaluation of finger-vein security system using Matlab tool,
and finally conclusion and future scope is given in section 5.

In this section, we review the prior work on finger vein
biometric security system over various applications. David et
al [1] introduced preliminary process to enhance the image
quality that worsen by light effect and produces noise by the
web camera, then segmented the vein pattern by using
adaptive threshold method and matched them using improved
template matching. The result shows that even the image
quality is not good and as long as the veins are clear with
some appropriate process can be used for personal

Wenming et al [2] proposed a structured personal
identification approach using finger vein Location and
Direction Coding (LDC). Initially finger vein imaging device
is designed using Near-InfraRed (NIR) light source, by which
a database for finger vein images is established. The
brightness difference in the finger vein image is used to
extract the vein pattern. Then finger vein LDC creates a
structured feature image for each finger vein. The structured
feature image is utilized to conduct the personal identification
with image database for finger vein, which includes 440 vein
images from 220 different fingers.

Hua-Bin et al [3] presented an algorithm based on adaptive
filtering and retinex method for enhancement of hand vein
images. The principal of the near-infrared hand vein image
acquisition is introduced, then the retinex method is used to
normalize hand vein images, and the adaptive smoothing
method is selected to estimate the illumination. Then the gray
cosine transform is used to enhance the discrimination of the
skin and the vein in hand vein images. Then a determination
criterion of hand vein is established to remove the false vein
blocks from the segmented hand vein images.

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308

Volume: 02 Issue: 12 | Dec-2013, Available @ 198
Shi et al [4] proposed a method to make low cost devices
using vein pattern images with low contrast, and high-quality
images. The method could extract the vein network
successfully as using high-quality images. The principle of
vein imaging is discussed to acquire the vein images which
could enhance the contrast and the algorithm of extracting the
vein pattern from low quality images.

Desong et al [5] presented a more secure and reliable user
identification mechanism using biometrics technology
equipped into the consumer electronics devices. The system
uses finger-vein identification system which provides high
security and reliability than other identification technology.
The algorithm composes of a feature extraction using radon
transform and singular value decomposition and classification
using a normalized distance measure.

Zhi et al [6] proposed a real-time embedded finger-vein
recognition system for authentication on mobile devices. The
system is implemented on a DSP platform and equipped with
a novel finger-vein recognition algorithm. The system takes
about 0.8 seconds to verify one input finger-vein sample and
achieves an equal error rate of 0.07 percent on a database of
100 subjects. The results proved that the finger-vein
recognition system is qualified for authentication on mobile

Li et al [7] proposed a modality-based bi-finger vein
verification system. Both the finger vein and finger shape
could be extracted from the single image acquired from the
sensor. The system includes the new finger vein network
extraction algorithm. The intersection of the forefinger and
middle finger as the origin is introduced to the coordinate
system, proposing a method including determining the region
of interest, the finger vein and shape features extraction and its
corresponding fusion verification.

Lin et al [8] presented an algorithm for segmenting the dorsal
hand vein image and extracting the vein skeleton. After gray
and size normalizing, Gaussian low pass filter and median
filter are used to eliminate the speck noise and the horizontal
strip scanning noise respectively. Then an improved NiBlack
algorithm segments the vein pattern and an area thresholding
algorithm removes the noise blocks from the vein pattern.

Jinfeng et al [9] focused on finger-vein enhancement and
segmentation based on Gabor filters in the spatial domain.
Considering the high randomicity of the finger-vein networks,
a bank of even symmetric Gabor filters with eight orientations
is firstly used to exploit vein information in images. Then,
image reconstruction is implemented to generate an image
containing an integrated finger-vein network.

Gongping et al [10] proposed a finger vein recognition method
based on a Personalized Best Bit Map (PBBM). The method is
rooted in a local binary pattern based method and then
inclined to use the best bits only for matching. The recognition
framework consists of preprocessing, feature extraction, and
matching. For evaluating the effectiveness of the method
extensive experimental designs are made and results show that
PBBM achieves better performance.

Naoto et al [11] proposed a method of personal identification
based on finger vein patterns. An image of a finger captured
under infrared light contains not only the vein pattern but also
irregular shading produced by the various thicknesses of the
finger bones and muscles. The method extracts the finger vein
pattern from the unclear image by using line tracking that
starts from various positions.

Finger vein structure is not easily seen in visible light. So the
device to capture the finger vein image composed of Near
InfraRed (NIR) Light Emitting Diodes (LED) of 850
nanometer wavelength and a Charge Coupled Device (CCD)
camera [13], [14]. Figure 1 shows the flow diagram of the
finger-vein based biometric security system.

The important step in finger-vein recognition is the vein
extraction from the background. The finger-vein images are
acquired by the use of NIR spectroscopy. The finger-vein
image obtained from the NIR spectroscopy appears to be
darker than the other regions of the finger. This is because the
blood vessels alone will absorb the rays.

The performance of the finger-vein extraction and matching
algorithm depends upon the quality of the input image.
Initially the image is enhanced to eliminate the noise using
oriented filter method. This also enhances the ridgelines, and
uses Gabor filter. Gabor filters are band-pass filters that are
having both orientation selective and frequency selective
properties. These utilize the directionality feature of the
finger-vein image and then the finger-vein is extracted from
the enhanced oriented filter image.

The feature vector is obtained by taking mean, standard
deviation and co-occurrence parameters. Let Ri
(x, y) be the
component image corresponding to
or sector Si. For i = 0,
1, 2… 47 and

[0o, 45o, 90o, 135o]. The features Mean
) and Standard deviation (Fi
), can be defined using
equations (1) and (2) respectively.


− =
Mi y x R Fi ) ) , ( ( θ θ

IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308

Volume: 02 Issue: 12 | Dec-2013, Available @ 199
The co-occurrence matrix (C) is given by,

{ } j v) I(t, i, s) I(r, v)); (t, s), ((r, j) C(i, = = =

Where, k is the number of pixels in Si,
θ Ri
is the sector of
the filtered image, and
θ Mi
is the mean of that sector.

The grey level value in each sector of the filtered image is
given as the finger code. Also the co-occurrence matrix (C)
with distance (1,1) i.e., one pixel below and one pixel right, in
each sector a feature, and contrast is calculated using the co-
occurrence matrix as given in equations (3) to improve the
recognition rate of this authentication system.

Fig 1 Flow diagram of finger-vein security system

Analysis of finger-vein based biometric security system has
been carried on an Intel Core 2 Duo CPU system with 2.10
GHz on a 32-bit Windows 7 Ultimate Operating System using
MATLAB. Since there is no finger-vein image database is
available, a database for 50 people between 21 years and 55
years old. From each people the forefinger, middle finger, and
ring finger of both hands are considered. The image which is
obtained from the real-time camera is shown in figure 2. The
image after preprocessing is shown in figure 3.

Fig 2 Input Image

Fig 3 Preprocessing

Fig 4 Feature Extraction

While matching two types of errors results in the finger-vein
based biometric verification security system. The errors are
false rejection rate and the false acceptance rate. False
rejection is a claim that a genuine image is considered as
impostor. False acceptance is a claim that an impostor image
is considered as genuine. When the false rejection rate and the
false acceptance rate are equal, then the performance of the
system is evaluated as equal error rate. This system is suitable
for mobile device applications with low computational
complexity and low power consumption.

In this paper, we presented a finger-vein based biometric
security system that can be used for security based electronic
devices. The method can extract the finger-vein feature for
recognition from the NIR images. This method uses single
sample and is convenient to the application. This work can be
extended with increasing the database for further verification.
IJRET: International Journal of Research in Engineering and Technology eISSN: 2319-1163 | pISSN: 2321-7308

Volume: 02 Issue: 12 | Dec-2013, Available @ 200
[1] David Mulyono, and Horng Shi Jinn, “A Study of
Finger Vein Biometric for Personal Identification”,
Proceedings of the IEEE International Symposium on
Biometrics and Security Technologies (ISBAST 2008),
pp. 1-8, 2008.
[2] Wenming Yang, Qing Rao, and Qingmin Liao,
“Personal Identification for Single Sample using Finger
Vein Location and Direction Coding”, Proceedings of
the IEEE International Conference on Hand-based
Biometrics (ICHB), pp. 1-6, 17-18 March 2011.
[3] Hua-Bin Wang, and Liang Tao, “Novel Algorithm for
Enhancement of Hand Vein Images based on Adaptive
Filtering and Retinex Method”, Proceedings of the
IEEE International Conference on Information Science
and Technology (ICIST), Wuhan, Hubei, China, pp.
857-860, 23-25 March 2012.
[4] Shi Zhao, Yiding Wang, and Yunhong Wang,
“Extracting Hand Vein Patterns from Low-Quality
Images: A New Biometric Technique using Low-Cost
Devices”, Fourth International Conference on Image
and Graphics (ICIG 2007), IEEE Computer Society, pp.
667-671, 22-24 Aug 2007.
[5] Desong Wang, Jianping Li, and Gokhan Memik, “User
Identification based on Finger-vein Patterns for
Consumer Electronics Devices”, IEEE Transactions on
Consumer Electronics, Vol. 56, No. 2, pp. 799-804,
May 2010.
[6] Zhi Liu, and Shangling Song, “An Embedded Real-
Time Finger-Vein Recognition System for Mobile
Devices”, IEEE Transactions on Consumer Electronics,
Vol. 58, No. 2, pp. 522-527, May 2012.
[7] Li Zhichao, Sun Dongmei, Liu Di, and Liu Hao, “Two
Modality-Based Bi-Finger Vein Verification System”,
2010 IEEE 10
International Conference on Signal
Processing (ICSP) pp. 1690-1693, 24-28 Oct 2010.
[8] Lin Yang, Xiangbin Liu, and Zhicheng Liu, “A
Skeleton Extracting Algorithm for Dorsal Hand Vein
Pattern”, 2010 International Conference on Computer
Application and System Modeling (ICCASM 2010), pp.
V13-92-V13-95, 22-24 Oct 2010.
[9] Jinfeng Yang, Jinli Yang, and Yihua Shi, “Finger-Vein
Segmentation Based on Multi-channel Even-symmetric
Gabor Filters”, IEEE International Conference on
Intelligent Computing and Intelligent Systems 2009
(ICIS 2009), Vol. 4, pp. 500-503, 20-22 Nov 2009.
[10] Gongping Yang, Xiaoming Xi, and Yilong Yin, “Finger
Vein Recognition Based on a Personalized Best Bit
Map”, Journal on Sensors, Vol. 12, pp. 1738-1757, doi:
10.3390/s120201738, 2012.
[11] Naoto Miura, Akio Nagasaka, and Takafumi Miyatake,
“Feature Extraction of Finger-vein Patterns based on
Repeated Line Tracking and its Application to Personal
Identification”, Machine Vision and Applications, Vol.
15, pp. 194-203, 2004.
[12] Lee H, S. H. Lee, T. Kim, and H. Bahn, “Secure User
Identification for Consumer Electronics Devices”, IEEE
Transactions on Consumer Electronics, Vol. 54, No. 4,
pp. 1798-1802, Nov. 2008.
[13] Hashimoto J., “Finger Vein Authentication Technology
and its Future”, 2006 Symposium on VLSI Circuits,
Digest of Technical Papers, pp. 5-8, 2006.
[14] Wu J. D., and S. H. Ye, “Driver Identification using
Finger-Vein Patterns with Random Transform and
Neural Network”, Expert System Applications, Vol. 36,
pp. 5793-5799, 2009.

Sponsor Documents

Or use your account on


Forgot your password?

Or register your new account on


Lost your password? Please enter your email address. You will receive a link to create a new password.

Back to log-in